Matt Cooper

As a data scientist and engineer, I have experience in R, python, SQL and NoSQL databases, cloud computing (AWS, GCP, and Azure), AI & Machine learning, NLP and topic modeling, parallel processing and multithreading, containerization (docker and virtual environments), and some web development (javascript and D3). I prefer working in linux, with a zsh terminal and coding using vim and tmux. As a researcher, I work with large datasets (100s of millions of records) to examine the effects of climate on human well-being. This involves processing global gridded climate datasets (historic data, as well as future climate simluations), paired with data on-the-ground outcomes, such as malaria rates, crop yields, or even the mood of social media posts, and analyzing relationships using statistical or machine learning models. In addition, I've held a number of industry positions, working with startups to rapidly prototype and deploy cloud architectures for applications in commodity futures, reinsurance, international development, consumer targeting, biodiversity modeling and grant monitoring. I'm capable of working independently and on teams, on multiple projects with competing deadlines. I've lead groups of academic researchers and junior data scientists, and worked successfully with distributed teams across timezones and cultural backgrounds.